Help us test cordn. We are looking for more feedback to improve it. Just start chatting with me https://cordn.net/p/npub1gzuushllat7pet0ccv9yuhygvc8ldeyhrgxuwg744dn5khnpk3gs3ea5ds It is private, secure, and cipher punk af

M tired boss

GMM🌞

GM🤙

Cordn.net is awesome, tbh. I’m not saying this because I helped build it or because it uses CVM as one of its fundamental pieces, but because it works! It delivers on its promises: private communications with pretty strong security guarantees, even when using a publicly hosted coordinator, and permissionless operation with a credible self‑sovereign story. I wish more people would start using it; it feels like the best alternative we have to finally drop Telegram, Signal, Discord, Slack, etc. Now we just need more people to join and share feedback. Just open https://cordn.net and start chatting. You don’t need to use your real npub if you don’t want to. I’m using it through Amber, tho. Amazing work, @Besao

👀 View quoted note →

This one is pretty juicy

Awesome Agents

Vibe Coding Is a Security Catastrophe: 69 Vulnerabilities Found Across 5 Major AI Coding Tools

A systematic security audit of Claude Code, Codex, Cursor, Replit, and Devin found 69 vulnerabilities in 15 test applications - zero CSRF protectio...

> "Coding agents cannot be trusted to design secure applications," Tenzai concluded. "They seem to be very prone to business logic vulnerabilities. While human developers bring intuitive understanding that helps them grasp how workflows should operate, agents lack this 'common sense.'" > Databricks' AI Red Team found that self-reflection prompts can improve security by 60-80% for Claude and up to 50% for GPT-4o. The tools can find their own vulnerabilities when asked. > But that is precisely the problem vibe coding was supposed to solve. The entire premise is that developers - or non-developers - can describe what they want and get working software. Requiring them to also know which security prompts to add defeats the purpose. View quoted note →